{ "train": { "log_interval": 200, "eval_interval": 3000, "seed": 42, "epochs": 1000, "learning_rate": 0.0002, "betas": [ 0.8, 0.99 ], "eps": 1e-09, "batch_size": 16, "bf16_run": true, "lr_decay": 0.99995, "segment_size": 16384, "init_lr_ratio": 1, "warmup_epochs": 0, "c_mel": 45, "c_kl": 1.0, "c_commit": 100, "skip_optimizer": true, "freeze_ZH_bert": false, "freeze_JP_bert": false, "freeze_EN_bert": false, "freeze_emo": false }, "data": { "training_files": "Data/BangDream/filelists/train.list", "validation_files": "Data/BangDream/filelists/val.list", "max_wav_value": 32768.0, "sampling_rate": 44100, "filter_length": 2048, "hop_length": 512, "win_length": 2048, "n_mel_channels": 128, "mel_fmin": 0.0, "mel_fmax": null, "add_blank": true, "n_speakers": 74, "cleaned_text": true, "spk2id": { "紗夜": 0, "沙綾": 1, "香澄": 2, "有咲": 3, "りみ": 4, "たえ": 5, "ロック": 6, "パレオ": 7, "レイヤ": 8, "チュチュ": 9, "千聖": 10, "イヴ": 11, "日菜": 12, "麻弥": 13, "蘭": 14, "モカ": 15, "巴": 16, "ひまり": 17, "つぐみ": 18, "はぐみ": 19, "花音": 20, "美咲": 21, "薫": 22, "こころ": 23, "つくし": 24, "七深": 25, "透子": 26, "ましろ": 27, "瑠唯": 28, "友希那": 29, "あこ": 30, "リサ": 31, "燐子": 32, "彩": 33, "燈": 34, "愛音": 35, "楽奈": 36, "そよ": 37, "立希": 38, "ますき": 39, "祥子": 40, "睦": 41, "海鈴": 42, "にゃむ": 43, "初華": 44, "三月七1": 45, "美空": 46, "芙蘿菈": 47, "克蕾兒": 48, "安德露": 49, "瑪莉亞貝菈": 50, "克拉迪亞": 51, "桃樂西": 52, "瑪麗安": 53, "八重神子1": 54, "娜塔莎": 55, "宵宫": 56, "派蒙11": 57, "派蒙13": 58, "派蒙3": 59, "派蒙7": 60, "派蒙8": 61, "派蒙9": 62, "派蒙10": 63, "派蒙6": 64, "派蒙4": 65, "派蒙1": 66, "派蒙2": 67, "派蒙15": 68, "派蒙16": 69, "派蒙14": 70, "派蒙12": 71, "派蒙5": 72, "纳西妲1": 73 } }, "model": { "use_spk_conditioned_encoder": true, "use_noise_scaled_mas": true, "use_mel_posterior_encoder": false, "use_duration_discriminator": true, "inter_channels": 192, "hidden_channels": 192, "filter_channels": 768, "n_heads": 2, "n_layers": 6, "kernel_size": 3, "p_dropout": 0.1, "resblock": "1", "resblock_kernel_sizes": [ 3, 7, 11 ], "resblock_dilation_sizes": [ [ 1, 3, 5 ], [ 1, 3, 5 ], [ 1, 3, 5 ] ], "upsample_rates": [ 8, 8, 2, 2, 2 ], "upsample_initial_channel": 512, "upsample_kernel_sizes": [ 16, 16, 8, 2, 2 ], "n_layers_q": 3, "use_spectral_norm": false, "gin_channels": 512, "slm": { "model": "./slm/wavlm-base-plus", "sr": 16000, "hidden": 768, "nlayers": 13, "initial_channel": 64 } }, "version": "2.3" }